CN114814750A - Radar calibration and verification method and device, computer equipment and storage medium - Google Patents

Radar calibration and verification method and device, computer equipment and storage medium Download PDF

Info

Publication number
CN114814750A
CN114814750A CN202210371627.2A CN202210371627A CN114814750A CN 114814750 A CN114814750 A CN 114814750A CN 202210371627 A CN202210371627 A CN 202210371627A CN 114814750 A CN114814750 A CN 114814750A
Authority
CN
China
Prior art keywords
point cloud
radar
cloud data
calibrated
coordinate system
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210371627.2A
Other languages
Chinese (zh)
Inventor
丁航
杨秉川
李陆洋
方牧
鲁豫杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Visionnav Robotics Shenzhen Co Ltd
Original Assignee
Visionnav Robotics Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Visionnav Robotics Shenzhen Co Ltd filed Critical Visionnav Robotics Shenzhen Co Ltd
Priority to CN202210371627.2A priority Critical patent/CN114814750A/en
Publication of CN114814750A publication Critical patent/CN114814750A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
    • G01S7/40—Means for monitoring or calibrating
    • G01S7/4052—Means for monitoring or calibrating by simulation of echoes
    • G01S7/4082—Means for monitoring or calibrating by simulation of echoes using externally generated reference signals, e.g. via remote reflector or transponder

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Radar Systems Or Details Thereof (AREA)

Abstract

本申请涉及一种雷达标定方法、装置、计算机设备、存储介质和计算机程序产品。方法包括：获取基准雷达按照预设路线移动过程中所接收的第一点云数据，以及同一场景下待标定雷达所接收的第二点云数据；在基准雷达移动至待标定雷达所在区域的过程中存在至少一个位置以使基准雷达的可视范围包含待标定雷达的可视范围；不同待标定雷达的可视范围内安装有不同形状的反光板；第一点云数据和第二点云数据均包含反光板反射的点云数据；根据匹配算法匹配第一点云数据和第二点云数据，得到待标定雷达在基准坐标系下的外参矩阵，基准坐标系为以基准雷达初始位置为原点所建立的坐标系。本方法可实现同时完成多个待标定雷达的标定工作，大大提高标定效率。

Figure 202210371627

The present application relates to a radar calibration method, apparatus, computer equipment, storage medium and computer program product. The method includes: acquiring the first point cloud data received by the reference radar in the process of moving according to the preset route, and the second point cloud data received by the radar to be calibrated in the same scene; the process of moving the reference radar to the area where the radar to be calibrated is located; There is at least one position in the reference radar so that the visible range of the reference radar includes the visible range of the radar to be calibrated; reflectors of different shapes are installed in the visible range of different radars to be calibrated; the first point cloud data and the second point cloud data Both contain the point cloud data reflected by the reflector; match the first point cloud data and the second point cloud data according to the matching algorithm to obtain the external parameter matrix of the radar to be calibrated in the reference coordinate system, and the reference coordinate system is the initial position of the reference radar as The coordinate system established by the origin. The method can realize the calibration work of multiple radars to be calibrated at the same time, and greatly improve the calibration efficiency.

Figure 202210371627

Description

雷达标定及验证方法、装置、计算机设备及存储介质Radar calibration and verification method, device, computer equipment and storage medium

技术领域technical field

本申请涉及激光雷达技术领域，特别是涉及一种雷达标定及验证方法、装置、计算机设备、存储介质和计算机程序产品。The present application relates to the technical field of lidar, and in particular, to a radar calibration and verification method, device, computer equipment, storage medium and computer program product.

背景技术Background technique

激光雷达通过向目标发射激光光束并接收从目标反射的光束来探测目标的位置和速度信息。激光雷达可以为无人驾驶提供真实可靠的目标信息。为了增强自动驾驶车辆对周围环境的感知能力和感知范围，通常会单车配置多个激光雷达，通过同时使用多个雷达进行视场拼接可以实现大视场。同时，多雷达也可以提高整个系统的鲁棒性。而由于安装位置的不同，多雷达的坐标系并不统一，这导致了多雷达输出的点云并不能统一到同一个坐标系，因此多激光雷达的外参标定至关重要。Lidar detects the position and velocity information of a target by emitting a laser beam at the target and receiving the beam reflected from the target. Lidar can provide real and reliable target information for unmanned driving. In order to enhance the perception ability and perception range of autonomous vehicles to the surrounding environment, a single vehicle is usually equipped with multiple lidars, and a large field of view can be achieved by using multiple radars at the same time for field-of-view splicing. At the same time, multiple radars can also improve the robustness of the entire system. Due to the different installation positions, the coordinate systems of multiple radars are not unified, which leads to the fact that the point clouds output by multiple radars cannot be unified into the same coordinate system, so the external parameter calibration of multiple lidars is very important.

相关技术中，激光雷达的外参标定，通常一次只能标定一个待标定雷达，标定效率较低。In the related art, in the external parameter calibration of lidar, usually only one radar to be calibrated can be calibrated at a time, and the calibration efficiency is low.

发明内容SUMMARY OF THE INVENTION

基于此，有必要针对上述技术问题，提供一种能够提高标定效率的雷达标定方法、装置、计算机设备、计算机可读存储介质和计算机程序产品。Based on this, it is necessary to provide a radar calibration method, apparatus, computer equipment, computer-readable storage medium and computer program product that can improve the calibration efficiency in view of the above technical problems.

第一方面，本申请提供了一种雷达标定方法。所述方法包括：In a first aspect, the present application provides a radar calibration method. The method includes:

获取基准雷达按照预设路线移动过程中所接收的第一点云数据，以及同一场景下待标定雷达所接收的第二点云数据；在所述基准雷达移动至所述待标定雷达所在区域的过程中存在至少一个位置以使所述基准雷达的可视范围包含所述待标定雷达的可视范围；不同待标定雷达的可视范围内安装有不同形状的反光板；所述第一点云数据和所述第二点云数据均包含所述反光板反射的点云数据；Obtain the first point cloud data received during the movement of the reference radar along the preset route, and the second point cloud data received by the radar to be calibrated in the same scene; when the reference radar moves to the area where the radar to be calibrated is located There is at least one position in the process so that the visible range of the reference radar includes the visible range of the radar to be calibrated; reflectors of different shapes are installed in the visible range of different radars to be calibrated; the first point cloud Both the data and the second point cloud data include point cloud data reflected by the reflector;

根据匹配算法匹配所述第一点云数据和所述第二点云数据，得到所述待标定雷达在基准坐标系下的外参矩阵，所述基准坐标系为以所述基准雷达所在初始位置为原点所建立的坐标系。Matching the first point cloud data and the second point cloud data according to a matching algorithm to obtain the external parameter matrix of the radar to be calibrated in a reference coordinate system, where the reference coordinate system is based on the initial position of the reference radar The coordinate system established for the origin.

在其中一个实施例中，在以所述基准雷达所在初始位置为原点，建立基准坐标系之后，还包括：In one of the embodiments, after establishing the reference coordinate system with the initial position where the reference radar is located as the origin, the method further includes:

获取在所述基准坐标系下，所述待标定雷达的初始坐标；obtaining the initial coordinates of the radar to be calibrated under the reference coordinate system;

将所述待标定雷达的初始坐标作为所述匹配算法的初始化矩阵参数；Taking the initial coordinates of the radar to be calibrated as the initialization matrix parameter of the matching algorithm;

所述根据匹配算法匹配所述第一点云数据和所述第二点云数据，得到所述待标定雷达在基准坐标系下的外参矩阵，包括：Matching the first point cloud data and the second point cloud data according to the matching algorithm to obtain the external parameter matrix of the radar to be calibrated in the reference coordinate system, including:

采用具有所述初始化矩阵参数的匹配算法匹配所述第一点云数据和所述第二点云数据，得到所述待标定雷达在基准坐标系下的外参矩阵。The first point cloud data and the second point cloud data are matched using the matching algorithm with the parameters of the initialization matrix to obtain the external parameter matrix of the radar to be calibrated in the reference coordinate system.

在其中一个实施例中，所述采用具有所述初始化矩阵参数的匹配算法匹配所述第一点云数据和所述第二点云数据，得到所述待标定雷达在基准坐标系下的外参矩阵，包括：In one embodiment, the matching algorithm with the initialization matrix parameter is used to match the first point cloud data and the second point cloud data to obtain the external parameters of the radar to be calibrated in the reference coordinate system matrix, including:

根据所述第一点云数据，生成待匹配地图数据；generating map data to be matched according to the first point cloud data;

根据所述待匹配地图数据，得到所述第一点云数据的标准正态分布参数；obtaining standard normal distribution parameters of the first point cloud data according to the map data to be matched;

根据所述第二点云数据和所述初始化矩阵参数，得到所述第二点云数据的标准正态分布参数；According to the second point cloud data and the initialization matrix parameters, the standard normal distribution parameters of the second point cloud data are obtained;

根据所述第一点云数据的标准正态分布参数和所述第二点云数据的标准正态分布参数，得到所述待标定雷达在所述基准坐标系下的外参矩阵。According to the standard normal distribution parameters of the first point cloud data and the standard normal distribution parameters of the second point cloud data, the external parameter matrix of the radar to be calibrated in the reference coordinate system is obtained.

在其中一个实施例中，所述根据匹配算法匹配所述第一点云数据和所述第二点云数据，得到所述待标定雷达在基准坐标系下的外参矩阵，包括：In one embodiment, the matching of the first point cloud data and the second point cloud data according to a matching algorithm to obtain an external parameter matrix of the radar to be calibrated in a reference coordinate system includes:

获取所述第一点云数据中采集时间范围与所述第二点云数据的采集时间范围相同的第一子点云数据；obtaining the first sub-point cloud data whose collection time range is the same as the collection time range of the second point cloud data in the first point cloud data;

根据匹配算法匹配所述第一子点云数据和所述第二点云数据，得到所述待标定雷达在基准坐标系下的外参矩阵。The first sub-point cloud data and the second point cloud data are matched according to a matching algorithm to obtain the external parameter matrix of the radar to be calibrated in the reference coordinate system.

在其中一个实施例中，所述反光板包括圆形反光板、三角形反光板和多边形反光板。In one of the embodiments, the reflector includes a circular reflector, a triangular reflector and a polygonal reflector.

第二方面，本申请还提供了一种雷达标定装置。所述装置包括：In a second aspect, the present application also provides a radar calibration device. The device includes:

点云获取模块，用于获取基准雷达按照预设路线移动过程中所接收的第一点云数据，以及同一场景下待标定雷达所接收的第二点云数据；在所述基准雷达移动至所述待标定雷达所在区域的过程中存在至少一个位置以使所述基准雷达的可视范围包含所述待标定雷达的可视范围；不同待标定雷达的可视范围内安装有不同形状的反光板；所述第一点云数据和所述第二点云数据均包含所述反光板反射的点云数据；The point cloud acquisition module is used to acquire the first point cloud data received by the reference radar in the process of moving according to the preset route, and the second point cloud data received by the radar to be calibrated in the same scene; There is at least one position in the process of the area where the radar to be calibrated is located so that the visible range of the reference radar includes the visible range of the radar to be calibrated; reflectors of different shapes are installed in the visible range of different radars to be calibrated ; The first point cloud data and the second point cloud data both include point cloud data reflected by the reflector;

点云匹配模块，用于根据匹配算法匹配所述第一点云数据和所述第二点云数据，得到所述待标定雷达在基准坐标系下的外参矩阵，所述基准坐标系为以所述基准雷达所在初始位置为原点所建立的坐标系。The point cloud matching module is used to match the first point cloud data and the second point cloud data according to the matching algorithm, and obtain the external parameter matrix of the radar to be calibrated under the reference coordinate system, and the reference coordinate system is The initial position of the reference radar is the coordinate system established by the origin.

第三方面，本申请还提供了一种计算机设备。所述计算机设备包括存储器和处理器，所述存储器存储有计算机程序，所述处理器执行所述计算机程序时实现以下步骤：In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

获取基准雷达按照预设路线移动过程中所接收的第一点云数据，以及同一场景下待标定雷达所接收的第二点云数据；在所述基准雷达移动至所述待标定雷达所在区域的过程中存在至少一个位置以使所述基准雷达的可视范围包含所述待标定雷达的可视范围；不同待标定雷达的可视范围内安装有不同形状的反光板；所述第一点云数据和所述第二点云数据均包含所述反光板反射的点云数据；Obtain the first point cloud data received during the movement of the reference radar along the preset route, and the second point cloud data received by the radar to be calibrated in the same scene; when the reference radar moves to the area where the radar to be calibrated is located There is at least one position in the process so that the visible range of the reference radar includes the visible range of the radar to be calibrated; reflectors of different shapes are installed in the visible range of different radars to be calibrated; the first point cloud Both the data and the second point cloud data include point cloud data reflected by the reflector;

根据匹配算法匹配所述第一点云数据和所述第二点云数据，得到所述待标定雷达在基准坐标系下的外参矩阵，所述基准坐标系为以所述基准雷达所在初始位置为原点所建立的坐标系。Matching the first point cloud data and the second point cloud data according to a matching algorithm to obtain the external parameter matrix of the radar to be calibrated in a reference coordinate system, where the reference coordinate system is based on the initial position of the reference radar The coordinate system established for the origin.

第四方面，本申请还提供了一种计算机可读存储介质。所述计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现以下步骤：In a fourth aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium has a computer program stored thereon, and when the computer program is executed by the processor, the following steps are implemented:

获取基准雷达按照预设路线移动过程中所接收的第一点云数据，以及同一场景下待标定雷达所接收的第二点云数据；在所述基准雷达移动至所述待标定雷达所在区域的过程中存在至少一个位置以使所述基准雷达的可视范围包含所述待标定雷达的可视范围；不同待标定雷达的可视范围内安装有不同形状的反光板；所述第一点云数据和所述第二点云数据均包含所述反光板反射的点云数据；Obtain the first point cloud data received during the movement of the reference radar along the preset route, and the second point cloud data received by the radar to be calibrated in the same scene; when the reference radar moves to the area where the radar to be calibrated is located There is at least one position in the process so that the visible range of the reference radar includes the visible range of the radar to be calibrated; reflectors of different shapes are installed in the visible range of different radars to be calibrated; the first point cloud Both the data and the second point cloud data include point cloud data reflected by the reflector;

根据匹配算法匹配所述第一点云数据和所述第二点云数据，得到所述待标定雷达在基准坐标系下的外参矩阵，所述基准坐标系为以所述基准雷达所在初始位置为原点所建立的坐标系。Matching the first point cloud data and the second point cloud data according to a matching algorithm to obtain the external parameter matrix of the radar to be calibrated in a reference coordinate system, where the reference coordinate system is based on the initial position of the reference radar The coordinate system established for the origin.

第五方面，本申请还提供了一种计算机程序产品。所述计算机程序产品，包括计算机程序，该计算机程序被处理器执行时实现以下步骤：In a fifth aspect, the present application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the following steps:

获取基准雷达按照预设路线移动过程中所接收的第一点云数据，以及同一场景下待标定雷达所接收的第二点云数据；在所述基准雷达移动至所述待标定雷达所在区域的过程中存在至少一个位置以使所述基准雷达的可视范围包含所述待标定雷达的可视范围；不同待标定雷达的可视范围内安装有不同形状的反光板；所述第一点云数据和所述第二点云数据均包含所述反光板反射的点云数据；Obtain the first point cloud data received during the movement of the reference radar along the preset route, and the second point cloud data received by the radar to be calibrated in the same scene; when the reference radar moves to the area where the radar to be calibrated is located There is at least one position in the process so that the visible range of the reference radar includes the visible range of the radar to be calibrated; reflectors of different shapes are installed in the visible range of different radars to be calibrated; the first point cloud Both the data and the second point cloud data include point cloud data reflected by the reflector;

根据匹配算法匹配所述第一点云数据和所述第二点云数据，得到所述待标定雷达在基准坐标系下的外参矩阵，所述基准坐标系为以所述基准雷达所在初始位置为原点所建立的坐标系。Matching the first point cloud data and the second point cloud data according to a matching algorithm to obtain the external parameter matrix of the radar to be calibrated in a reference coordinate system, where the reference coordinate system is based on the initial position of the reference radar The coordinate system established for the origin.

上述雷达标定方法、装置、计算机设备、存储介质和计算机程序产品，通过获取基准雷达按照预设路线移动过程中所接收的第一点云数据，以及同一场景下待标定雷达所接收的第二点云数据；在所述基准雷达移动至所述待标定雷达所在区域的过程中存在至少一个位置以使所述基准雷达的可视范围包含所述待标定雷达的可视范围；不同待标定雷达的可视范围内安装有不同形状的反光板；所述第一点云数据和所述第二点云数据均包含所述反光板反射的点云数据；根据匹配算法匹配所述第一点云数据和所述第二点云数据，得到所述待标定雷达在基准坐标系下的外参矩阵，所述基准坐标系为以所述基准雷达所在初始位置为原点所建立的坐标系。本申请通过基准雷达沿着预设路线移动的过程中所接收到的全场景的第一点云数据，与同一场景下多个待标定雷达所接收的局部场景的第二点云数据进行匹配，分别得到每个待标定雷达的外参矩阵，可实现同时完成多个待标定雷达的标定工作，大大提高标定效率。同时，不同待标定雷达的可视范围内安装有不同形状的反光板，可使得接收到的点云数据强度更强，使得标定结果更加准确。The above-mentioned radar calibration method, device, computer equipment, storage medium and computer program product obtain the first point cloud data received during the movement of the reference radar according to the preset route, and the second point received by the to-be-calibrated radar in the same scene cloud data; there is at least one position during the movement of the reference radar to the area where the radar to be calibrated is located so that the visible range of the reference radar includes the visible range of the radar to be calibrated; Reflectors of different shapes are installed within the visible range; both the first point cloud data and the second point cloud data include point cloud data reflected by the reflector; the first point cloud data is matched according to a matching algorithm and the second point cloud data to obtain the external parameter matrix of the radar to be calibrated under the reference coordinate system, where the reference coordinate system is a coordinate system established with the initial position of the reference radar as the origin. In the present application, the first point cloud data of the whole scene received during the movement of the reference radar along the preset route is matched with the second point cloud data of the local scene received by multiple radars to be calibrated in the same scene, The external parameter matrix of each radar to be calibrated can be obtained separately, so that the calibration of multiple radars to be calibrated can be completed at the same time, and the calibration efficiency can be greatly improved. At the same time, reflectors of different shapes are installed in the visible range of different radars to be calibrated, which can make the received point cloud data stronger and make the calibration results more accurate.

第六方面，本申请还提供了一种雷达标定的验证方法。所述方法包括：In a sixth aspect, the present application also provides a verification method for radar calibration. The method includes:

获取待验证雷达扫描预设参考平面所接收的第三点云数据；Obtain the third point cloud data received by the radar scanning preset reference plane to be verified;

根据所述待验证雷达的外参矩阵将各所述待验证雷达接收到的第三点云数据转换到同一坐标系中，得到第四点云数据；所述外参矩阵为根据上述雷达标定方法得到；The third point cloud data received by each radar to be verified is converted into the same coordinate system according to the external parameter matrix of the radar to be verified, and the fourth point cloud data is obtained; the external parameter matrix is based on the above radar calibration method get;

根据所述第四点云数据的平整度，以确定雷达标定结果是否准确。Whether the radar calibration result is accurate is determined according to the flatness of the fourth point cloud data.

第七方面，本申请还提供了一种雷达标定的验证装置。所述装置包括：In a seventh aspect, the present application also provides a verification device for radar calibration. The device includes:

第一验证模块，用于获取待验证雷达扫描预设参考平面所接收的第三点云数据；a first verification module, used to obtain the third point cloud data received by the radar scanning preset reference plane to be verified;

第二验证模块，用于根据所述待验证雷达的外参矩阵将各所述待验证雷达接收到的第三点云数据转换到同一坐标系中，得到第四点云数据；所述外参矩阵为根据上述雷达标定方法得到；The second verification module is used to convert the third point cloud data received by each of the radars to be verified into the same coordinate system according to the external parameter matrix of the radar to be verified to obtain fourth point cloud data; the external parameter The matrix is obtained according to the above radar calibration method;

第三验证模块，用于根据所述第四点云数据的平整度，以确定雷达标定结果是否准确。The third verification module is configured to determine whether the radar calibration result is accurate according to the flatness of the fourth point cloud data.

第八方面，本申请还提供了一种计算机设备。所述计算机设备包括存储器和处理器，所述存储器存储有计算机程序，所述处理器执行所述计算机程序时实现以下步骤：In an eighth aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

获取待验证雷达扫描预设参考平面所接收的第三点云数据；Obtain the third point cloud data received by the radar scanning preset reference plane to be verified;

根据所述待验证雷达的外参矩阵将各所述待验证雷达接收到的第三点云数据转换到同一坐标系中，得到第四点云数据；所述外参矩阵为根据上述雷达标定方法得到；The third point cloud data received by each radar to be verified is converted into the same coordinate system according to the external parameter matrix of the radar to be verified, and the fourth point cloud data is obtained; the external parameter matrix is based on the above radar calibration method get;

根据所述第四点云数据的平整度，以确定雷达标定结果是否准确。Whether the radar calibration result is accurate is determined according to the flatness of the fourth point cloud data.

第九方面，本申请还提供了一种计算机可读存储介质。所述计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现以下步骤：In a ninth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium has a computer program stored thereon, and when the computer program is executed by the processor, the following steps are implemented:

获取待验证雷达扫描预设参考平面所接收的第三点云数据；Obtain the third point cloud data received by the radar scanning preset reference plane to be verified;

根据所述待验证雷达的外参矩阵将各所述待验证雷达接收到的第三点云数据转换到同一坐标系中，得到第四点云数据；所述外参矩阵为根据上述雷达标定方法得到；The third point cloud data received by each radar to be verified is converted into the same coordinate system according to the external parameter matrix of the radar to be verified, and the fourth point cloud data is obtained; the external parameter matrix is based on the above radar calibration method get;

根据所述第四点云数据的平整度，以确定雷达标定结果是否准确。Whether the radar calibration result is accurate is determined according to the flatness of the fourth point cloud data.

第十方面，本申请还提供了一种计算机程序产品。所述计算机程序产品，包括计算机程序，该计算机程序被处理器执行时实现以下步骤：In a tenth aspect, the present application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the following steps:

获取待验证雷达扫描预设参考平面所接收的第三点云数据；Obtain the third point cloud data received by the radar scanning preset reference plane to be verified;

根据所述待验证雷达的外参矩阵将各所述待验证雷达接收到的第三点云数据转换到同一坐标系中，得到第四点云数据；所述外参矩阵为根据上述雷达标定方法得到；The third point cloud data received by each radar to be verified is converted into the same coordinate system according to the external parameter matrix of the radar to be verified, and the fourth point cloud data is obtained; the external parameter matrix is based on the above radar calibration method get;

根据所述第四点云数据的平整度，以确定雷达标定结果是否准确。Whether the radar calibration result is accurate is determined according to the flatness of the fourth point cloud data.

上述雷达标定的验证方法、装置、计算机设备、存储介质和计算机程序产品，通过获取待验证雷达扫描预设参考平面所接收的第三点云数据；根据所述待验证雷达的外参矩阵将各所述待验证雷达接收到的第三点云数据转换到同一坐标系中，得到第四点云数据；所述外参矩阵为根据上述雷达标定方法得到；根据所述第四点云数据的平整度，以确定雷达标定结果是否准确。本申请通过根据上述雷达标定方法得到的待验证雷达的外参矩阵将各个待验证雷达接收到的第三点云数据转换到同一坐标系中，根据同一坐标系中的点云数据的平整度，判断待验证雷达之间的一致性，以此验证雷达标定结果是否准确，可实现对待验证雷达的准确验证。The verification method, device, computer equipment, storage medium and computer program product for the above-mentioned radar calibration are obtained by obtaining the third point cloud data received by the radar to be verified by scanning the preset reference plane; according to the external parameter matrix of the radar to be verified, each The third point cloud data received by the radar to be verified is converted into the same coordinate system to obtain the fourth point cloud data; the external parameter matrix is obtained according to the above-mentioned radar calibration method; according to the flattening of the fourth point cloud data degree to determine whether the radar calibration result is accurate. The present application converts the third point cloud data received by each radar to be verified into the same coordinate system through the external parameter matrix of the radar to be verified obtained according to the above radar calibration method, and according to the flatness of the point cloud data in the same coordinate system, By judging the consistency between the radars to be verified, to verify whether the calibration results of the radars are accurate, the accurate verification of the radars to be verified can be achieved.

附图说明Description of drawings

图1为一个实施例中雷达标定方法的应用环境图；1 is an application environment diagram of a radar calibration method in one embodiment;

图2为一个实施例中雷达标定方法的流程示意图；2 is a schematic flowchart of a radar calibration method in one embodiment;

图3为一个实施例中得到待标定雷达在基准坐标系下的外参矩阵的流程示意图；3 is a schematic flowchart of obtaining the external parameter matrix of the radar to be calibrated in the reference coordinate system in one embodiment;

图4为一个实施例中步骤204的流程示意图；4 is a schematic flowchart of step 204 in one embodiment;

图5为一个实施例中雷达标定的验证方法的流程示意图；5 is a schematic flowchart of a verification method for radar calibration in one embodiment;

图6为一个实施例中雷达标定及验证方法的流程示意图；6 is a schematic flowchart of a radar calibration and verification method in one embodiment;

图7为一个实施例中雷达标定装置的结构框图；7 is a structural block diagram of a radar calibration device in one embodiment;

图8为一个实施例中计算机设备的内部结构图。FIG. 8 is a diagram of the internal structure of a computer device in one embodiment.

具体实施方式Detailed ways

为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

本申请实施例提供的雷达标定方法，可以应用于如图1所示的应用环境中。其中，基准雷达104安装于或放置于无人叉车102上，无人叉车102可沿着预设路线108移动，预设路线108途经待标定雷达106所在区域以及待标定雷达106的可视范围区域，在待标定雷达106的可视范围区域安装有不同形状的反光板(反光板图中未示出)。无人叉车102还可以替换为其他自动驾驶车辆，实际应用场景可以是工厂或工业园区等大型场景。The radar calibration method provided in the embodiment of the present application can be applied to the application environment shown in FIG. 1 . The reference radar 104 is installed or placed on the unmanned forklift 102 , and the unmanned forklift 102 can move along a preset route 108 , and the preset route 108 passes through the area where the radar 106 to be calibrated is located and the visible range area of the radar 106 to be calibrated , reflectors of different shapes are installed in the visible range area of the radar 106 to be calibrated (the reflectors are not shown in the figure). The unmanned forklift 102 can also be replaced with other self-driving vehicles, and the actual application scenarios can be large-scale scenarios such as factories or industrial parks.

计算机设备获取基准雷达按照预设路线移动过程中所接收的第一点云数据，以及同一场景下待标定雷达所接收的第二点云数据；其中，在基准雷达移动至待标定雷达所在区域的过程中存在至少一个位置以使基准雷达的可视范围包含待标定雷达的可视范围；不同待标定雷达的可视范围内安装有不同形状的反光板；第一点云数据和第二点云数据均包含反光板反射的点云数据；计算机设备根据匹配算法匹配第一点云数据和第二点云数据，得到待标定雷达在基准坐标系下的外参矩阵，基准坐标系为以基准雷达所在初始位置为原点所建立的坐标系。其中，计算机设备可以是终端也可以是服务器，还可以是终端获取第一点云数据和第二点云数据后发送至服务器进行处理。The computer equipment obtains the first point cloud data received during the movement of the reference radar along the preset route, and the second point cloud data received by the radar to be calibrated in the same scene; wherein, when the reference radar moves to the area where the radar to be calibrated is located. There is at least one position in the process so that the visible range of the reference radar includes the visible range of the radar to be calibrated; reflectors of different shapes are installed in the visible range of different radars to be calibrated; the first point cloud data and the second point cloud The data includes the point cloud data reflected by the reflector; the computer equipment matches the first point cloud data and the second point cloud data according to the matching algorithm, and obtains the external parameter matrix of the radar to be calibrated in the reference coordinate system, and the reference coordinate system is the reference radar. The initial position is the coordinate system established by the origin. The computer device may be a terminal or a server, or the terminal may acquire the first point cloud data and the second point cloud data and send them to the server for processing.

在一个实施例中，如图2所示，提供了一种雷达标定方法，以该方法应用于服务器为例进行说明，包括以下步骤：In one embodiment, as shown in FIG. 2, a radar calibration method is provided, and the method is applied to a server as an example for description, including the following steps:

步骤202，获取基准雷达按照预设路线移动过程中所接收的第一点云数据，以及同一场景下待标定雷达所接收的第二点云数据；其中，在基准雷达移动至待标定雷达所在区域的过程中存在至少一个位置以使基准雷达的可视范围包含待标定雷达的可视范围；不同待标定雷达的可视范围内安装有不同形状的反光板；第一点云数据和第二点云数据均包含反光板反射的点云数据。Step 202: Obtain the first point cloud data received by the reference radar during the movement process according to the preset route, and the second point cloud data received by the to-be-calibrated radar in the same scene; wherein, when the reference radar moves to the area where the to-be-calibrated radar is located There is at least one position in the process to make the visible range of the reference radar include the visible range of the radar to be calibrated; reflectors of different shapes are installed in the visible range of different radars to be calibrated; the first point cloud data and the second point The cloud data all contain point cloud data reflected by the reflector.

服务器获取基准雷达按照预设路线移动过程中所接收的第一点云数据，以及同一场景下待标定雷达所接收的第二点云数据。其中，同一场景是指具有相同的可视范围区域，可以是室内场景，也可以是室外场景，例如在同一个工厂或者同一个工业园区内的场景。本实施例中，基准雷达只有1个，待标定雷达为多个，且多个待标定雷达的位置各不相同，即待标定雷达的可视范围区域也就不相同。在基准雷达移动至待标定雷达所在区域的过程中，存在至少一个位置以使基准雷达的可视范围包含待标定雷达的可视范围，例如，预设路线途经待标定雷达所在区域以及待标定雷达的可视范围区域，可以使得基准雷达的可视范围包含待标定雷达的可视范围，目的是使基准雷达能够扫描到待标定雷达所扫描到的点云数据，且对每个待标定雷达都是如此。同时，在不同的待标定雷达的可视范围内安装有不同形状的反光板，例如在待标定雷达A的可视范围内安装圆形的反光板，待标定雷达B的可视范围内安装有三角形的反光板，在待标定雷达C的可视范围内安装有正方形的反光板，在待标定雷达D的可视范围内安装有五边形的反光板，依此类推。由于不同的待标定雷达的可视范围内安装有不同形状的反光板，待标定雷达能够接收到可视范围内所安装的反光板反射的点云数据，而基准雷达在移动过程中存在基准雷达的可视范围包含待标定雷达的可视范围的情形，即基准雷达能够接收到待标定雷达所接收到可视范围内安装的反光板发射的点云数据，即第一点云数据和第二点云数据均包含有反光板反射的点云数据。The server obtains the first point cloud data received during the movement of the reference radar along the preset route, and the second point cloud data received by the to-be-calibrated radar in the same scene. The same scene refers to an area with the same visible range, which may be an indoor scene or an outdoor scene, such as a scene in the same factory or the same industrial park. In this embodiment, there is only one reference radar and multiple radars to be calibrated, and the positions of the multiple radars to be calibrated are different, that is, the visible range areas of the radars to be calibrated are also different. In the process of moving the reference radar to the area where the radar to be calibrated, there is at least one position so that the visible range of the reference radar includes the visible range of the radar to be calibrated, for example, the preset route passes through the area where the radar to be calibrated and the radar to be calibrated The visible range area of the reference radar can make the visible range of the reference radar include the visible range of the radar to be calibrated. The purpose is to enable the reference radar to scan the point cloud data scanned by the radar to be calibrated, and for each radar to be calibrated. It is so. At the same time, reflectors of different shapes are installed within the visible range of different radars to be calibrated. For example, a circular reflector is installed within the visible range of radar A to be calibrated, and a reflector of different shapes is installed within the visible range of radar B to be calibrated. For the triangular reflector, a square reflector is installed within the visible range of the radar C to be calibrated, and a pentagonal reflector is installed within the visible range of the radar D to be calibrated, and so on. Since reflectors of different shapes are installed in the visible range of different radars to be calibrated, the radars to be calibrated can receive the point cloud data reflected by the reflectors installed in the visible range, and the reference radar has a reference radar during the movement process. The visible range includes the visible range of the radar to be calibrated, that is, the reference radar can receive the point cloud data emitted by the reflectors installed within the visible range received by the radar to be calibrated, that is, the first point cloud data and the second point cloud data. The point cloud data contains the point cloud data reflected by the reflector.

本实施例中，不同待标定雷达固定安装在不同的位置，因此不同待标定雷达的可视范围可以有重叠，也可以完全没有重叠。基准雷达沿着预设路线沿途获取第一点云数据，而待标定雷达获取相应可视范围内的第二点云数据，即第一点云数据包括了所有待标定雷达所接收到的第二点云数据。In this embodiment, different radars to be calibrated are fixedly installed in different positions, so the visible ranges of different radars to be calibrated may overlap or not overlap at all. The reference radar obtains the first point cloud data along the preset route, and the radar to be calibrated obtains the second point cloud data within the corresponding visible range, that is, the first point cloud data includes the second point cloud data received by all the radars to be calibrated. point cloud data.

步骤204，根据匹配算法匹配第一点云数据和第二点云数据，得到待标定雷达在基准坐标系下的外参矩阵，其中，基准坐标系为以基准雷达所在初始位置为原点所建立的坐标系。Step 204: Match the first point cloud data and the second point cloud data according to the matching algorithm to obtain the external parameter matrix of the radar to be calibrated under the reference coordinate system, wherein the reference coordinate system is established with the initial position of the reference radar as the origin. Coordinate System.

服务器根据匹配算法匹配第一点云数据和第二点云数据，得到待标定雷达在基准坐标系下的外参矩阵。其中，匹配算法指的是点云匹配算法，目的是在于比较两者之间的差异，并得到两者之间的关系。点云匹配算法常用的有ICP(Iterative Closest Point，迭代最近点)算法和NDT(Normal Distribution Transform，正态分布变换)算法。基准坐标系是以基准雷达所在初始位置为原点所建立的坐标系。例如，可以以基准雷达所在初始位置为原点，基准雷达所在初始位置可以选择距离任一待标定雷达3-5米范围内的位置，在基准雷达所在水平面上构建基准坐标系中的任意两个坐标轴，如X轴和Y轴。同时使得待标定雷达与基准雷达处于同一水平面上，可以降低匹配过程中的计算复杂度。The server matches the first point cloud data and the second point cloud data according to the matching algorithm, and obtains the external parameter matrix of the radar to be calibrated in the reference coordinate system. Among them, the matching algorithm refers to the point cloud matching algorithm, the purpose is to compare the difference between the two, and obtain the relationship between the two. The commonly used point cloud matching algorithms are the ICP (Iterative Closest Point, iterative closest point) algorithm and the NDT (Normal Distribution Transform, normal distribution transform) algorithm. The reference coordinate system is a coordinate system established with the initial position of the reference radar as the origin. For example, the initial position of the reference radar can be used as the origin, and the initial position of the reference radar can be selected within 3-5 meters from any radar to be calibrated, and any two coordinates in the reference coordinate system can be constructed on the horizontal plane where the reference radar is located. axes, such as the X and Y axes. At the same time, the radar to be calibrated and the reference radar are placed on the same horizontal plane, which can reduce the computational complexity in the matching process.

上述雷达标定方法，通过获取基准雷达按照预设路线移动过程中所接收的第一点云数据，以及同一场景下待标定雷达所接收的第二点云数据；在基准雷达移动至待标定雷达所在区域的过程中存在至少一个位置以使基准雷达的可视范围包含待标定雷达的可视范围；不同待标定雷达的可视范围内安装有不同形状的反光板；第一点云数据和第二点云数据均包含反光板反射的点云数据；根据匹配算法匹配第一点云数据和所述第二点云数据，得到待标定雷达在基准坐标系下的外参矩阵，基准坐标系为以基准雷达所在初始位置为原点所建立的坐标系。本申请实施例通过基准雷达沿着预设路线的过程中所接收到的全场景的第一点云数据，与同一场景下多个待标定雷达所接收的局部场景的第二点云数据进行匹配，分别得到每个待标定雷达的外参矩阵，可实现同时完成多个待标定雷达的标定工作，大大提高标定效率。同时，不同待标定雷达的可视范围内安装有不同形状的反光板，可使得接收到的点云数据强度更强，使得标定结果更加准确。The above radar calibration method obtains the first point cloud data received by the reference radar in the process of moving according to the preset route, and the second point cloud data received by the radar to be calibrated in the same scene; when the reference radar moves to the location of the radar to be calibrated There is at least one position in the process of the area so that the visible range of the reference radar includes the visible range of the radar to be calibrated; reflectors of different shapes are installed in the visible range of different radars to be calibrated; the first point cloud data and the second The point cloud data includes the point cloud data reflected by the reflector; the first point cloud data and the second point cloud data are matched according to the matching algorithm, and the external parameter matrix of the radar to be calibrated under the reference coordinate system is obtained. The initial position of the reference radar is the coordinate system established by the origin. In this embodiment of the present application, the first point cloud data of the whole scene received by the reference radar along the preset route is matched with the second point cloud data of the local scene received by multiple radars to be calibrated in the same scene , and obtain the external parameter matrix of each radar to be calibrated, which can realize the calibration of multiple radars to be calibrated at the same time, and greatly improve the calibration efficiency. At the same time, reflectors of different shapes are installed in the visible range of different radars to be calibrated, which can make the received point cloud data stronger and make the calibration results more accurate.

在一个实施例中，在以基准雷达所在初始位置为原点，建立基准坐标系之后，还包括：In one embodiment, after establishing the reference coordinate system with the initial position where the reference radar is located as the origin, the method further includes:

获取在基准坐标系下待标定雷达的初始坐标。Obtain the initial coordinates of the radar to be calibrated in the reference coordinate system.

建立基准坐标系后，可以通过手工测量或者设备测量的方式，得到各待标定雷达在基准坐标系下相对于原点的偏移量，即可得到各待标定雷达的初始坐标。After the reference coordinate system is established, the offset of each radar to be calibrated relative to the origin in the reference coordinate system can be obtained by manual measurement or equipment measurement, and then the initial coordinates of each radar to be calibrated can be obtained.

将待标定雷达的初始坐标作为匹配算法的初始化矩阵参数。The initial coordinates of the radar to be calibrated are taken as the initialization matrix parameters of the matching algorithm.

将待标定雷达的初始坐标作为初始距离值，将初始距离值输入至匹配算法中作为初始化外参矩阵参数。The initial coordinates of the radar to be calibrated are used as the initial distance value, and the initial distance value is input into the matching algorithm as the initialized external parameter matrix parameter.

根据匹配算法匹配第一点云数据和第二点云数据，得到待标定雷达在基准坐标系下的外参矩阵，包括：Match the first point cloud data and the second point cloud data according to the matching algorithm to obtain the external parameter matrix of the radar to be calibrated in the reference coordinate system, including:

采用具有初始化矩阵参数的匹配算法匹配第一点云数据和第二点云数据，得到待标定雷达在基准坐标系下的外参矩阵。A matching algorithm with initialization matrix parameters is used to match the first point cloud data and the second point cloud data to obtain the external parameter matrix of the radar to be calibrated in the reference coordinate system.

本实施例通过将获取的待标定雷达的初始坐标作为匹配算法的初始化矩阵参数，有利于提高匹配算法的匹配精度，同时可以提高匹配算法的运算速度。In this embodiment, by using the acquired initial coordinates of the radar to be calibrated as the initialization matrix parameter of the matching algorithm, the matching accuracy of the matching algorithm can be improved, and the operation speed of the matching algorithm can be improved at the same time.

在一个实施例中，如图3所示，采用具有初始化矩阵参数的匹配算法匹配第一点云数据和第二点云数据，得到待标定雷达在基准坐标系下的外参矩阵，包括：In one embodiment, as shown in Figure 3, a matching algorithm with initialization matrix parameters is used to match the first point cloud data and the second point cloud data to obtain the external parameter matrix of the radar to be calibrated in the reference coordinate system, including:

步骤302，根据第一点云数据，生成待匹配地图数据。Step 302: Generate map data to be matched according to the first point cloud data.

将基准雷达在沿着预设路线移动过程中所接收的第一点云数据，使用建图工具生成待匹配地图数据，例如，可以使用SLAM(simultaneous localization and mapping，同步定位与建图)生成待匹配地图数据。Use the mapping tool to generate the first point cloud data received by the reference radar during the movement along the preset route to be matched. For example, SLAM (simultaneous localization and mapping) can be used to generate the to-be-matched map data. Match map data.

步骤304，根据待匹配地图数据，得到第一点云数据的标准正态分布参数。Step 304 , obtain standard normal distribution parameters of the first point cloud data according to the map data to be matched.

本实施例中，可以使用体素网格化方法将待匹配地图数据进行下采样，得到第一目标点云数据，计算每个网格中的第一目标点云数据的标准正态分布，进而得到第一点云数据在每个网格中对应的标准正态分布。其中，网格的大小及网格数量可以根据需求进行设定。In this embodiment, the voxel grid method can be used to downsample the map data to be matched to obtain the first target point cloud data, calculate the standard normal distribution of the first target point cloud data in each grid, and then Get the standard normal distribution corresponding to the first point cloud data in each grid. Among them, the size of the grid and the number of grids can be set according to requirements.

步骤306，根据第二点云数据和初始化矩阵参数，得到第二点云数据的标准正态分布参数。Step 306: Obtain standard normal distribution parameters of the second point cloud data according to the second point cloud data and the initialization matrix parameters.

本实施例中，可以将第二点云数据和初始化矩阵参数的乘积，作为第二点云初始数据，将第二点云初始数据根据体素网格化方法进行下采样，得到第二点云目标数据，计算每个第二点云目标数据落入第一点云数据对应的网格中概率，从而得到第二点云目标数据对应的标准正态分布参数。In this embodiment, the product of the second point cloud data and the initialization matrix parameters can be used as the second point cloud initial data, and the second point cloud initial data is down-sampled according to the voxel grid method to obtain the second point cloud target data, and calculate the probability of each second point cloud target data falling into the grid corresponding to the first point cloud data, so as to obtain standard normal distribution parameters corresponding to the second point cloud target data.

步骤308，根据第一点云数据的标准正态分布参数和第二点云数据的标准正态分布参数，得到待标定雷达在基准坐标系下的外参矩阵。Step 308 , according to the standard normal distribution parameters of the first point cloud data and the standard normal distribution parameters of the second point cloud data, obtain the external parameter matrix of the radar to be calibrated in the reference coordinate system.

根据体素网格化方法将第一点云数据和第二点云数据分别进行下采样；将第一点云数据所在空间划分多个三维网格，对于每个网格，基于网格内的点云分布计算相应的概率密度函数；针对每个第二点云数据，根据初始化矩阵参数，将每个第二点云数据映射到第一点云数据所在坐标系中，得到对应的映射点；根据网格的第一点云数据的正态分布参数计算每个映射点落在对应的网格中的概率，根据概率得到坐标变换参数对应的分数值；通过不断优化分数值，直至满足预设收敛条件后，得到最优分数值对应的坐标变换参数，即待标定雷达在基准坐标系下的外参矩阵。其中，预设收敛条件可以是预设迭代次数、预设分数值等。例如，预设收敛条件还可以是当分数值达到某一最大值时，后面继续迭代预设次数后得到的分数值均小于该最大值，则停止迭代，并将该最大值对应的坐标变换参数作为待标定雷达在基准坐标系下的外参矩阵。The first point cloud data and the second point cloud data are respectively downsampled according to the voxel gridding method; the space where the first point cloud data is located is divided into multiple three-dimensional grids, and for each grid, based on the The point cloud distribution calculates the corresponding probability density function; for each second point cloud data, according to the initialization matrix parameters, each second point cloud data is mapped to the coordinate system where the first point cloud data is located, and the corresponding mapping point is obtained; Calculate the probability of each mapping point falling in the corresponding grid according to the normal distribution parameters of the first point cloud data of the grid, and obtain the score value corresponding to the coordinate transformation parameter according to the probability; by continuously optimizing the score value until the preset value is satisfied After the convergence conditions, the coordinate transformation parameters corresponding to the optimal score value are obtained, that is, the external parameter matrix of the radar to be calibrated in the reference coordinate system. The preset convergence condition may be a preset number of iterations, a preset score value, and the like. For example, the preset convergence condition may also be that when the score value reaches a certain maximum value, and the score value obtained after continuing to iterate for a preset number of times is smaller than the maximum value, the iteration is stopped, and the coordinate transformation parameter corresponding to the maximum value is used as The external parameter matrix of the radar to be calibrated in the reference coordinate system.

在一个具体的示例中，使用NDT算法进行第一点云数据和第二点云数据的匹配如下：In a specific example, the NDT algorithm is used to match the first point cloud data and the second point cloud data as follows:

(1)根据体素网格化方法将第一点云数据和第二点云数据分别进行下采样。根据体素网格化方法将输入的点云数据创建为一个三维体素栅格，可把体素栅格想象为微小的空间三维立方体的集合，然后在每个体素内，即，三维立方体内，用体素中所有点的重心来近似显示体素中其他点，这样该体素内所有点就用一个重心点最终表示，对于所有体素处理后得到过滤后的点云。即在减少点云的数据量的同时，保持点云的形状特征。(1) Downsampling the first point cloud data and the second point cloud data respectively according to the voxel gridding method. The input point cloud data is created as a 3D voxel grid according to the voxel grid method. The voxel grid can be imagined as a collection of tiny spatial 3D cubes, and then within each voxel, that is, the 3D cube , use the center of gravity of all points in the voxel to approximate other points in the voxel, so that all points in the voxel are finally represented by a center of gravity point, and the filtered point cloud is obtained after processing all voxels. That is, while reducing the data volume of the point cloud, the shape characteristics of the point cloud are maintained.

(2)将第一点云数据所在空间划分为多个三维网格，针对每个网格，基于网格内的点云分布计算其概率密度函数。(2) Divide the space where the first point cloud data is located into a plurality of three-dimensional grids, and for each grid, calculate its probability density function based on the point cloud distribution in the grid.

均值：

Figure BDA0003588929530000111
Mean:
Figure BDA0003588929530000111

其中，

Figure BDA0003588929530000112
表示一个网格中所有的第一点云数据。in,
Figure BDA0003588929530000112
Represents all the first point cloud data in a grid.

协方差矩阵：

Figure BDA0003588929530000113
Covariance matrix:
Figure BDA0003588929530000113

一个网格的概率密度函数为：

Figure BDA0003588929530000121
The probability density function of a grid is:
Figure BDA0003588929530000121

(3)针对每个第二点云数据，根据初始化矩阵参数，将每个第二点云数据映射到第一点云数据所在坐标系中，得到对应的映射点；根据网格的正态分布参数计算每个映射点落在对应的网格中的概率

Figure BDA0003588929530000122
并将每个映射点落在对应网格中的概率之和作为本轮坐标变换参数T的分数值
Figure BDA0003588929530000123
进行评估。(3) For each second point cloud data, according to the initialization matrix parameters, map each second point cloud data to the coordinate system where the first point cloud data is located to obtain the corresponding mapping point; according to the normal distribution of the grid The parameter calculates the probability that each mapped point falls in the corresponding grid
Figure BDA0003588929530000122
The sum of the probabilities of each mapping point falling in the corresponding grid is taken as the fractional value of the coordinate transformation parameter T of this round
Figure BDA0003588929530000123
to evaluate.

Figure BDA0003588929530000124
Figure BDA0003588929530000124

Figure BDA0003588929530000125
Figure BDA0003588929530000125

其中，

Figure BDA0003588929530000126
代表映射点，n代表映射点对应的网格数，d1和d2代表由标准正态分布进阶到混合正态分布的常数，
Figure BDA0003588929530000127
为映射点均值向量，∑k为映射点协方差。in,
Figure BDA0003588929530000126
represents the mapping point, n represents the grid number corresponding to the mapping point, d1 and d2 represent the constants from standard normal distribution to mixed normal distribution,
Figure BDA0003588929530000127
is the mean vector of mapping points, and ∑ k is the covariance of mapping points.

NDT算法中三维变换矩阵

Figure BDA0003588929530000128
可以表示为：Three-dimensional transformation matrix in NDT algorithm
Figure BDA0003588929530000128
It can be expressed as:

Figure BDA0003588929530000129
Figure BDA0003588929530000129

式中，

Figure BDA00035889295300001210
t＝[tx ty tz]，r＝[rx ry rz]，s＝sinΦ，c＝cosΦ，tx，ty，tz分别代表在x、y、z坐标轴上的位置偏移量，rx，ry，rz分别代表在x、y、z方向上的角度偏移量，Φ为映射点与第一点云之间的夹角。In the formula,
Figure BDA00035889295300001210
t=[t x t y t z ], r=[r x r y r z ], s=sinΦ, c=cosΦ, t x , ty , t z respectively represent the The position offsets, r x , ry , and r z represent the angular offsets in the x, y, and z directions, respectively, and Φ is the angle between the mapping point and the first point cloud.

(4)使用牛顿优化算法对上述的分数值

Figure BDA00035889295300001211
进行优化，即取
Figure BDA00035889295300001212
的最小值。牛顿算法也称为快速下降法，其基本公式如下：(4) Use the Newton optimization algorithm to evaluate the above fractional values
Figure BDA00035889295300001211
optimize, take
Figure BDA00035889295300001212
the minimum value of . Newton's algorithm is also known as the fast descent method, and its basic formula is as follows:

HΔp＝-gHΔp=-g

g为雅克比矩阵，表达式如下：g is the Jacobian matrix, and the expression is as follows:

Figure BDA00035889295300001213
Figure BDA00035889295300001213

Figure BDA00035889295300001214
表示映射点与映射点均值的偏差。
Figure BDA00035889295300001214
Represents the deviation of the mapped point from the mean of the mapped point.

H为海森矩阵，公式如下：H is the Hessian matrix, the formula is as follows:

Figure BDA0003588929530000131
Figure BDA0003588929530000131

(5)不断循环步骤(3)～(4)，直至满足预设收敛条件为止。(5) Repeat steps (3) to (4) continuously until the preset convergence condition is satisfied.

在一个实施例中，如图4所示，根据匹配算法匹配第一点云数据和第二点云数据，得到待标定雷达在基准坐标系下的外参矩阵，包括：In one embodiment, as shown in FIG. 4 , the first point cloud data and the second point cloud data are matched according to the matching algorithm to obtain the external parameter matrix of the radar to be calibrated in the reference coordinate system, including:

步骤402，获取第一点云数据中采集时间范围与第二点云数据的采集时间范围相同的第一子点云数据。Step 402: Acquire first sub-point cloud data in the first point cloud data whose collection time range is the same as the collection time range of the second point cloud data.

由于第一点云数据是基准雷达按照预设路线移动的过程中所接收到的点云数据，即第一点云数据包括了整个预设路线上的可视范围内的点云数据，因此，可以根据采集时间范围，将第一点云数据中，与第二点云数据的采集时间范围相同的第一子点云数据挑选出。即，使得第一子点云数据所对应的可视范围与第二点云数据所对应的可视范围相同，可以提高第一子点云数据和第二点云数据的匹配程度。每个待标定雷达所接收的第二点云数据对应一个第一子点云数据。Since the first point cloud data is the point cloud data received by the reference radar in the process of moving along the preset route, that is, the first point cloud data includes the point cloud data within the visible range on the entire preset route, therefore, According to the collection time range, the first sub-point cloud data in the first point cloud data that has the same collection time range as the second point cloud data may be selected. That is, making the visible range corresponding to the first sub-point cloud data and the visible range corresponding to the second point cloud data the same, can improve the matching degree of the first sub-point cloud data and the second point cloud data. The second point cloud data received by each radar to be calibrated corresponds to a first sub-point cloud data.

步骤404，根据匹配算法匹配第一子点云数据和第二点云数据，得到待标定雷达在基准坐标系下的外参矩阵。Step 404: Match the first sub-point cloud data and the second point cloud data according to the matching algorithm to obtain the external parameter matrix of the radar to be calibrated in the reference coordinate system.

服务器可以根据匹配算法匹配第二点云数据及对应采集时间范围内的第一子点云数据，得到第二点云数据对应的待标定雷达在基准坐标系下的外参矩阵。The server can match the second point cloud data and the first sub-point cloud data within the corresponding acquisition time range according to the matching algorithm, and obtain the external parameter matrix of the radar to be calibrated corresponding to the second point cloud data in the reference coordinate system.

在一个实施例中，反光板包括圆形反光板、三角形反光板和多边形反光板。In one embodiment, the reflectors include circular reflectors, triangular reflectors, and polygonal reflectors.

本实施例中，不同的待标定雷达的可视范围内安装有不同形状的反光板，反光板包括圆形反光板、三角形反光板、四边形反光板、五边形反光板及其他的多边形反光板。在同一个待标定雷达的可视范围内不限定具体的形状，只需要不同的待标定雷达的可视范围对应不同形状的反光板。具体反光板的大小、材质等根据实际应用场景进行选择，在此不进行进一步限定。不同的待标定雷达的可视范围安装不同形状的反光板，可以使得不同的待标定雷达接收到的第二点云数据之间的强度差异性增大，在使用匹配算法匹配第一点云数据和第二点云数据时，可以提高点云数据匹配的精确度。In this embodiment, reflectors of different shapes are installed within the visible range of different radars to be calibrated. The reflectors include circular reflectors, triangular reflectors, quadrilateral reflectors, pentagonal reflectors, and other polygonal reflectors. . The specific shape is not limited within the visible range of the same radar to be calibrated, and it is only required that the visible ranges of different radars to be calibrated correspond to reflectors of different shapes. The specific size and material of the reflector are selected according to the actual application scenario, and are not further limited here. Different shapes of reflectors are installed in the visible range of different radars to be calibrated, which can increase the intensity difference between the second point cloud data received by different radars to be calibrated. When using a matching algorithm to match the first point cloud data When matching with the second point cloud data, the matching accuracy of the point cloud data can be improved.

在一个实施例中，如图5所示，提供了一种雷达标定的验证方法，以该方法应用于服务器为例进行说明，包括以下步骤：In one embodiment, as shown in FIG. 5 , a verification method for radar calibration is provided, and the method is applied to a server as an example for description, including the following steps:

步骤502，获取待验证雷达扫描预设参考平面所接收的第三点云数据。Step 502: Acquire third point cloud data received by the radar scanning preset reference plane to be verified.

服务器获取待验证雷达扫描预设参考平面所接收的第三点云数据。其中，待验证雷达包括多个，多个待验证雷达是基于同一基准雷达进行标定的。预设参考平面可以是任意一个平面，例如，可以是一块平坦的地面或者墙面。在一个可能的实现方式中，可以获取多个待验证雷达同时扫描预设参考平面所接收的第三点云数据。The server obtains the third point cloud data received by the radar scanning preset reference plane to be verified. Among them, there are multiple radars to be verified, and the multiple radars to be verified are calibrated based on the same reference radar. The preset reference plane can be any plane, for example, it can be a flat ground or a wall. In a possible implementation manner, the third point cloud data received by multiple radars to be verified scanning the preset reference plane at the same time may be acquired.

步骤504，根据待验证雷达的外参矩阵将各待验证雷达接收到的第三点云数据转换到同一坐标系中，得到第四点云数据；其中，外参矩阵为根据上述雷达标定方法得到。Step 504: Convert the third point cloud data received by each radar to be verified into the same coordinate system according to the external parameter matrix of the radar to be verified, to obtain the fourth point cloud data; wherein, the external parameter matrix is obtained according to the above radar calibration method. .

根据上述雷达标定方法得到待验证雷达的外参矩阵，外参矩阵表征待标定雷达的坐标系与世界坐标系之间的转换关系。服务器根据待验证雷达的外参矩阵可以将所有待验证雷达接收到的第三点云数据转换到同一坐标系中，得到第四点云数据。According to the above radar calibration method, the external parameter matrix of the radar to be verified is obtained, and the external parameter matrix represents the transformation relationship between the coordinate system of the radar to be calibrated and the world coordinate system. The server can convert the third point cloud data received by all the radars to be verified into the same coordinate system according to the external parameter matrix of the radar to be verified, and obtain the fourth point cloud data.

步骤506，根据第四点云数据的平整度，以确定雷达标定结果是否准确。Step 506: Determine whether the radar calibration result is accurate according to the flatness of the fourth point cloud data.

将需要进行验证的待验证雷达接收到的第三点云数据转换到同一坐标系中，得到需要进行验证的待验证雷达接收到的第三点云数据对应的第四点云数据，根据第四点云数据的平整度，确定雷达标定结果是否准确。其中，雷达标定结果通常可以是待验证雷达对应的外参矩阵。若第四点云数据的平整度大于平整度阈值，则确定雷达标定结果准确；若第四点云数据的平整度小于平整度阈值，则确定雷达标定结果不准确。Convert the third point cloud data received by the radar to be verified that needs to be verified into the same coordinate system, and obtain the fourth point cloud data corresponding to the third point cloud data received by the radar to be verified to be verified, according to the fourth point cloud data. The flatness of the point cloud data determines whether the radar calibration result is accurate. Among them, the radar calibration result can usually be the external parameter matrix corresponding to the radar to be verified. If the flatness of the fourth point cloud data is greater than the flatness threshold, it is determined that the radar calibration result is accurate; if the flatness of the fourth point cloud data is less than the flatness threshold, it is determined that the radar calibration result is inaccurate.

在一个可能的实现方式中，可以根据同一坐标系中的第四点云数据在同一坐标轴上的坐标所在的范围大小，确定第四点云数据的平整度。例如，若第四点云数据在X轴和Y轴上的坐标范围均大于Z轴上的坐标范围，则根据Z轴上的坐标范围，确定第四点云数据的平整度，Z轴上的坐标范围越小，第四点云数据的平整度越好；或者，可以建立一个标准参考平面，该标准参考平面与X轴、Y轴所在平面相平行，也可以是X轴和Y轴所在平面，计算各第四点云数据到该标准参考平面的距离，根据各第四点云数据到该标准参考平面的距离范围，确定第四点云数据的平整度，若第四点云数据到该标准参考平面的距离范围越小，则第四点云数据的平整度越好。In a possible implementation manner, the flatness of the fourth point cloud data may be determined according to the size of the range where the coordinates of the fourth point cloud data in the same coordinate system on the same coordinate axis are located. For example, if the coordinate range of the fourth point cloud data on the X-axis and the Y-axis is larger than the coordinate range on the Z-axis, the flatness of the fourth point cloud data is determined according to the coordinate range on the Z-axis. The smaller the coordinate range, the better the flatness of the fourth point cloud data; alternatively, a standard reference plane can be established, which is parallel to the plane where the X and Y axes are located, or the plane where the X and Y axes are located. , calculate the distance from each fourth point cloud data to the standard reference plane, and determine the flatness of the fourth point cloud data according to the distance range of each fourth point cloud data to the standard reference plane. The smaller the distance range of the standard reference plane, the better the flatness of the fourth point cloud data.

在另一个可能的实现方式中，分别计算各个待验证雷达对应的第四点云数据的正态分布(Normal distribution)，比较各待验证雷达对应的第四点云数据的正态分布之间的差异，根据正态分布之间的差异，确定第四点云数据的平整度。正态分布之间的差异越小，第四点云数据的平整度越好。In another possible implementation manner, the normal distribution (Normal distribution) of the fourth point cloud data corresponding to each radar to be verified is calculated respectively, and the difference between the normal distributions of the fourth point cloud data corresponding to each radar to be verified is compared. Difference, according to the difference between the normal distributions, to determine the flatness of the fourth point cloud data. The smaller the difference between the normal distributions, the better the flatness of the fourth point cloud data.

上述雷达标定的验证方法，通过获取待验证雷达扫描预设参考平面所接收的第三点云数据；根据待验证雷达的外参矩阵将各待验证雷达接收到的第三点云数据转换到同一坐标系中，得到第四点云数据；外参矩阵为根据上述雷达标定方法得到；根据第四点云数据的平整度，以确定雷达标定结果是否准确。本实施例通过根据上述雷达标定方法得到的待验证雷达的外参矩阵将各个待验证雷达接收到的第三点云数据转换到同一坐标系中，根据同一坐标系中的点云数据的平整度，判断待验证雷达之间的一致性，以此验证雷达标定结果是否准确，可实现对待验证雷达的准确验证。The verification method of the above radar calibration is to obtain the third point cloud data received by the scanning preset reference plane of the radar to be verified; according to the external parameter matrix of the radar to be verified, the third point cloud data received by each radar to be verified is converted into the same one. In the coordinate system, the fourth point cloud data is obtained; the external parameter matrix is obtained according to the above radar calibration method; according to the flatness of the fourth point cloud data, it is determined whether the radar calibration result is accurate. In this embodiment, the third point cloud data received by each radar to be verified is converted into the same coordinate system by the external parameter matrix of the radar to be verified obtained according to the above radar calibration method, and the flatness of the point cloud data in the same coordinate system , judging the consistency between the radars to be verified, so as to verify whether the calibration results of the radars are accurate, which can realize the accurate verification of the radars to be verified.

在一个实施例中，如图6所示，提供了一种雷达标定及验证方法，包括以下步骤：In one embodiment, as shown in FIG. 6, a radar calibration and verification method is provided, including the following steps:

步骤602，获取基准雷达按照预设路线移动过程中所接收的第一点云数据，以及同一场景下待标定雷达所接收的第二点云数据；其中，在基准雷达移动至待标定雷达所在区域的过程中存在至少一个位置以使基准雷达的可视范围包含待标定雷达的可视范围；不同待标定雷达的可视范围内安装有不同形状的反光板；第一点云数据和第二点云数据均包含反光板反射的点云数据。Step 602, obtain the first point cloud data received by the reference radar during the movement process according to the preset route, and the second point cloud data received by the to-be-calibrated radar in the same scene; wherein, when the reference radar moves to the area where the to-be-calibrated radar is located There is at least one position in the process to make the visible range of the reference radar include the visible range of the radar to be calibrated; reflectors of different shapes are installed in the visible range of different radars to be calibrated; the first point cloud data and the second point The cloud data all contain point cloud data reflected by the reflector.

第一点云数据为基准雷达按照预设路线移动过程中所扫描到的点云数据，第二点云数据为同一场景下待标定雷达扫描到的点云数据，预设路线途经待标定雷达所在区域以及待标定雷达的可视范围区域，以使得基准雷达的可视范围包含待标定雷达的可视范围。同时，不同待标定雷达的可视范围内安装有不同形状的反光板，例如在待标定雷达A的可视范围内安装圆形的反光板，待标定雷达B的可视范围内安装有三角形的反光板，在待标定雷达C的可视范围内安装有正方形的反光板，在待标定雷达D的可视范围内安装有五边形的反光板，依此类推。The first point cloud data is the point cloud data scanned by the reference radar in the process of moving along the preset route, the second point cloud data is the point cloud data scanned by the radar to be calibrated in the same scene, and the preset route passes through the location of the radar to be calibrated. area and the visible range area of the radar to be calibrated, so that the visible range of the reference radar includes the visible range of the radar to be calibrated. At the same time, reflectors of different shapes are installed within the visible range of different radars to be calibrated. For example, a circular reflector is installed within the visible range of radar A to be calibrated, and a triangular reflector is installed within the visible range of radar B to be calibrated. For the reflector, a square reflector is installed within the visible range of the radar C to be calibrated, a pentagonal reflector is installed within the visible range of the radar D to be calibrated, and so on.

步骤604，根据NDT匹配算法匹配第一点云数据和第二点云数据，得到待标定雷达在基准坐标系下的外参矩阵，其中，基准坐标系为以基准雷达所在初始位置为原点所建立的坐标系。Step 604: Match the first point cloud data and the second point cloud data according to the NDT matching algorithm to obtain the external parameter matrix of the radar to be calibrated under the reference coordinate system, wherein the reference coordinate system is established with the initial position of the reference radar as the origin. coordinate system.

外参矩阵用于表征待标定雷达的坐标系与基准坐标系之间的变换关系。基准坐标系是以基准雷达所在初始位置为原点所建立的坐标系。例如，可以以基准雷达所在初始位置为原点，基准雷达所在初始位置可以选择距离任一待标定雷达3-5米范围内的位置。The external parameter matrix is used to represent the transformation relationship between the coordinate system of the radar to be calibrated and the reference coordinate system. The reference coordinate system is a coordinate system established with the initial position of the reference radar as the origin. For example, the initial position of the reference radar can be taken as the origin, and the initial position of the reference radar can be selected within a range of 3-5 meters from any radar to be calibrated.

步骤606，获取待验证雷达扫描预设参考平面所接收的第三点云数据。Step 606: Obtain third point cloud data received by the radar scanning preset reference plane to be verified.

服务器获取待验证雷达扫描预设参考平面所接收的第三点云数据。其中，待验证雷达包括多个，多个待验证雷达是基于同一基准雷达进行标定的。本实施例中，可以将步骤602至步骤604中的待标定雷达作为待验证雷达进行标定结果的准确性验证。The server obtains the third point cloud data received by the radar scanning preset reference plane to be verified. Among them, there are multiple radars to be verified, and the multiple radars to be verified are calibrated based on the same reference radar. In this embodiment, the to-be-calibrated radar in steps 602 to 604 may be used as the to-be-verified radar to verify the accuracy of the calibration result.

步骤608，根据待验证雷达的外参矩阵将各待验证雷达接收到的第三点云数据转换到同一坐标系中，得到第四点云数据；其中，外参矩阵为根据上述雷达标定方法得到。Step 608: Convert the third point cloud data received by each radar to be verified into the same coordinate system according to the external parameter matrix of the radar to be verified to obtain the fourth point cloud data; wherein, the external parameter matrix is obtained according to the above radar calibration method .

根据上述雷达标定方法得到待验证雷达的外参矩阵后，根据待验证雷达的外参矩阵将各待验证雷达接收到的第三点云数据转换到同一坐标系中，得到第四点云数据。After the external parameter matrix of the radar to be verified is obtained according to the above radar calibration method, the third point cloud data received by each radar to be verified is converted into the same coordinate system according to the external parameter matrix of the radar to be verified to obtain the fourth point cloud data.

步骤610，根据第四点云数据的平整度，以确定雷达标定结果是否准确。Step 610: Determine whether the radar calibration result is accurate according to the flatness of the fourth point cloud data.

通过设置平整度阈值，若第四点云数据的平整度大于平整度阈值，则确定雷达标定结果准确；若第四点云数据的平整度小于平整度阈值，则确定雷达标定结果不准确。By setting the flatness threshold, if the flatness of the fourth point cloud data is greater than the flatness threshold, the radar calibration result is determined to be accurate; if the flatness of the fourth point cloud data is less than the flatness threshold, the radar calibration result is determined to be inaccurate.

上述雷达标定及验证方法，通过雷达标定方法可以实现同时对多个待标定雷达进行标定，而且可以得到精度较高的标定结果，即各个待标定雷达对应的外参矩阵，然后再通过雷达标定的验证方法对前面得到的标定结果进行验证，实现对雷达标定结果的准确验证。The above radar calibration and verification methods can be used to calibrate multiple radars to be calibrated at the same time through the radar calibration method, and can obtain calibration results with higher accuracy, that is, the external parameter matrix corresponding to each radar to be calibrated. The verification method verifies the calibration results obtained above, and realizes the accurate verification of the radar calibration results.

应该理解的是，虽然如上所述的各实施例所涉及的流程图中的各个步骤按照箭头的指示依次显示，但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明，这些步骤的执行并没有严格的顺序限制，这些步骤可以以其它的顺序执行。而且，如上所述的各实施例所涉及的流程图中的至少一部分步骤可以包括多个步骤或者多个阶段，这些步骤或者阶段并不必然是在同一时刻执行完成，而是可以在不同的时刻执行，这些步骤或者阶段的执行顺序也不必然是依次进行，而是可以与其它步骤或者其它步骤中的步骤或者阶段的至少一部分轮流或者交替地执行。It should be understood that, although the steps in the flowcharts involved in the above embodiments are sequentially displayed according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, the execution of these steps is not strictly limited to the order, and the steps may be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but may be performed at different times The execution order of these steps or phases is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of the steps or phases in the other steps.

基于同样的发明构思，本申请实施例还提供了一种用于实现上述所涉及的雷达标定方法的雷达标定装置。该装置所提供的解决问题的实现方案与上述方法中所记载的实现方案相似，故下面所提供的一个或多个雷达标定装置实施例中的具体限定可以参见上文中对于雷达标定方法的限定，在此不再赘述。Based on the same inventive concept, an embodiment of the present application also provides a radar calibration device for implementing the above-mentioned radar calibration method. The solution to the problem provided by the device is similar to the implementation described in the above method, so the specific limitations in one or more embodiments of the radar calibration device provided below can refer to the above limitations on the radar calibration method, It is not repeated here.

在一个实施例中，如图7所示，提供了一种雷达标定装置，包括：点云获取模块702和点云匹配模块704，其中：In one embodiment, as shown in FIG. 7, a radar calibration apparatus is provided, including: a point cloud acquisition module 702 and a point cloud matching module 704, wherein:

点云获取模块702，用于获取基准雷达按照预设路线移动过程中所接收的第一点云数据，以及同一场景下待标定雷达所接收的第二点云数据；在所述基准雷达移动至所述待标定雷达所在区域的过程中存在至少一个位置以使所述基准雷达的可视范围包含所述待标定雷达的可视范围；不同待标定雷达的可视范围内安装有不同形状的反光板；所述第一点云数据和所述第二点云数据均包含所述反光板反射的点云数据；The point cloud acquisition module 702 is used to acquire the first point cloud data received by the reference radar in the process of moving according to the preset route, and the second point cloud data received by the radar to be calibrated under the same scene; when the reference radar moves to There is at least one position in the process of the area where the radar to be calibrated is located, so that the visible range of the reference radar includes the visible range of the radar to be calibrated; different shapes of reflective lights are installed in the visible range of different radars to be calibrated board; both the first point cloud data and the second point cloud data include point cloud data reflected by the reflector;

点云匹配模块704，用于根据匹配算法匹配所述第一点云数据和所述第二点云数据，得到所述待标定雷达在基准坐标系下的外参矩阵，所述基准坐标系为以所述基准雷达所在初始位置为原点所建立的坐标系。The point cloud matching module 704 is used to match the first point cloud data and the second point cloud data according to a matching algorithm, and obtain the external parameter matrix of the radar to be calibrated under the reference coordinate system, and the reference coordinate system is A coordinate system established with the initial position of the reference radar as the origin.

在一个实施例中，雷达标定装置还包括初始化模块，用于：In one embodiment, the radar calibration device further includes an initialization module for:

获取在所述基准坐标系下，所述待标定雷达的初始坐标；obtaining the initial coordinates of the radar to be calibrated under the reference coordinate system;

将所述待标定雷达的初始坐标作为所述匹配算法的初始化矩阵参数；Taking the initial coordinates of the radar to be calibrated as the initialization matrix parameter of the matching algorithm;

所述点云匹配模块704，还用于：The point cloud matching module 704 is also used for:

采用具有所述初始化矩阵参数的匹配算法匹配所述第一点云数据和所述第二点云数据，得到所述待标定雷达在基准坐标系下的外参矩阵。The first point cloud data and the second point cloud data are matched using the matching algorithm with the parameters of the initialization matrix to obtain the external parameter matrix of the radar to be calibrated in the reference coordinate system.

在一个实施例中，所述点云匹配模块704，还用于：In one embodiment, the point cloud matching module 704 is further configured to:

根据所述第一点云数据，生成待匹配地图数据；generating map data to be matched according to the first point cloud data;

根据所述待匹配地图数据，得到所述第一点云数据的标准正态分布参数；obtaining standard normal distribution parameters of the first point cloud data according to the map data to be matched;

根据所述第二点云数据和所述初始化矩阵参数，得到所述第二点云数据的标准正态分布参数；According to the second point cloud data and the initialization matrix parameters, the standard normal distribution parameters of the second point cloud data are obtained;

根据所述第一点云数据的标准正态分布参数和所述第二点云数据的标准正态分布参数，得到所述待标定雷达在所述基准坐标系下的外参矩阵。According to the standard normal distribution parameters of the first point cloud data and the standard normal distribution parameters of the second point cloud data, the external parameter matrix of the radar to be calibrated in the reference coordinate system is obtained.

在其中一个实施例中，点云匹配模块704，还用于：In one embodiment, the point cloud matching module 704 is further configured to:

获取所述第一点云数据中采集时间范围与所述第二点云数据的采集时间范围相同的第一子点云数据；obtaining the first sub-point cloud data whose collection time range is the same as the collection time range of the second point cloud data in the first point cloud data;

根据匹配算法匹配所述第一子点云数据和所述第二点云数据，得到所述待标定雷达在基准坐标系下的外参矩阵。The first sub-point cloud data and the second point cloud data are matched according to a matching algorithm to obtain the external parameter matrix of the radar to be calibrated in the reference coordinate system.

基于同样的发明构思，本申请实施例还提供了一种用于实现上述所涉及的雷达标定的验证方法的雷达标定的验证装置。该装置所提供的解决问题的实现方案与上述方法中所记载的实现方案相似，故下面所提供的一个或多个雷达标定装置实施例中的具体限定可以参见上文中对于雷达标定的验证方法的限定，在此不再赘述。Based on the same inventive concept, an embodiment of the present application further provides a radar calibration verification device for implementing the above-mentioned radar calibration verification method. The solution to the problem provided by the device is similar to the implementation described in the above method, so the specific limitations in one or more embodiments of the radar calibration device provided below can refer to the above section on the verification method for radar calibration. limitations, which will not be repeated here.

在一个实施例中，提供了一种雷达标定的验证装置，包括：In one embodiment, a verification device for radar calibration is provided, comprising:

第一验证模块，用于获取待验证雷达扫描预设参考平面所接收的第三点云数据；a first verification module, used to obtain the third point cloud data received by the radar scanning preset reference plane to be verified;

第二验证模块，用于根据所述待验证雷达的外参矩阵将各所述待验证雷达接收到的第三点云数据转换到同一坐标系中，得到第四点云数据；所述外参矩阵为根据上述雷达标定方法得到；The second verification module is used to convert the third point cloud data received by each of the radars to be verified into the same coordinate system according to the external parameter matrix of the radar to be verified to obtain fourth point cloud data; the external parameter The matrix is obtained according to the above radar calibration method;

第三验证模块，用于根据所述第四点云数据的平整度，以确定雷达标定结果是否准确。The third verification module is configured to determine whether the radar calibration result is accurate according to the flatness of the fourth point cloud data.

上述雷达标定装置或者雷达标定的验证装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于计算机设备中的处理器中，也可以以软件形式存储于计算机设备中的存储器中，以便于处理器调用执行以上各个模块对应的操作。Each module in the above radar calibration device or the radar calibration verification device can be implemented in whole or in part by software, hardware and combinations thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

在一个实施例中，提供了一种计算机设备，该计算机设备可以是服务器，其内部结构图可以如图8所示。该计算机设备包括通过系统总线连接的处理器、存储器和网络接口。其中，该计算机设备的处理器用于提供计算和控制能力。该计算机设备的存储器包括非易失性存储介质和内存储器。该非易失性存储介质存储有操作系统、计算机程序和数据库。该内存储器为非易失性存储介质中的操作系统和计算机程序的运行提供环境。该计算机设备的数据库用于存储点云数据。该计算机设备的网络接口用于与外部的终端通过网络连接通信。该计算机程序被处理器执行时以实现一种雷达标定方法或者一种雷达标定的验证方法。In one embodiment, a computer device is provided, and the computer device may be a server, and its internal structure diagram may be as shown in FIG. 8 . The computer device includes a processor, memory, and a network interface connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes non-volatile storage media and internal memory. The nonvolatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the execution of the operating system and computer programs in the non-volatile storage medium. The database of the computer device is used to store the point cloud data. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program, when executed by the processor, implements a radar calibration method or a radar calibration verification method.

本领域技术人员可以理解，图8中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备的限定，具体的计算机设备可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。Those skilled in the art can understand that the structure shown in FIG. 8 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.

在一个实施例中，提供了一种计算机设备，包括存储器和处理器，存储器中存储有计算机程序，该处理器执行计算机程序时实现上述实施例中雷达标定方法的步骤。In one embodiment, a computer device is provided, including a memory and a processor, where a computer program is stored in the memory, and when the processor executes the computer program, the steps of the radar calibration method in the above embodiment are implemented.

在一个实施例中，提供了一种计算机可读存储介质，其上存储有计算机程序，计算机程序被处理器执行时实现上述实施例中雷达标定方法的步骤。In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, implements the steps of the radar calibration method in the foregoing embodiment.

在一个实施例中，提供了一种计算机程序产品，包括计算机程序，该计算机程序被处理器执行时实现上述实施例中雷达标定方法的步骤。In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps of the radar calibration method in the above embodiment.

在一个实施例中，提供了一种计算机设备，包括存储器和处理器，存储器中存储有计算机程序，该处理器执行计算机程序时实现上述实施例中雷达标定的验证方法的步骤。In one embodiment, a computer device is provided, including a memory and a processor, where a computer program is stored in the memory, and when the processor executes the computer program, the processor implements the steps of the radar calibration verification method in the foregoing embodiment.

在一个实施例中，提供了一种计算机可读存储介质，其上存储有计算机程序，计算机程序被处理器执行时实现上述实施例中雷达标定的验证方法的步骤。In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, implements the steps of the radar calibration verification method in the above-mentioned embodiment.

在一个实施例中，提供了一种计算机程序产品，包括计算机程序，该计算机程序被处理器执行时实现上述实施例中雷达标定的验证方法的步骤。In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps of the radar calibration verification method in the above embodiment.

本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的计算机程序可存储于一非易失性计算机可读取存储介质中，该计算机程序在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的各实施例中所使用的对存储器、数据库或其它介质的任何引用，均可包括非易失性和易失性存储器中的至少一种。非易失性存储器可包括只读存储器(Read-OnlyMemory，ROM)、磁带、软盘、闪存、光存储器、高密度嵌入式非易失性存储器、阻变存储器(ReRAM)、磁变存储器(Magnetoresistive Random Access Memory，MRAM)、铁电存储器(Ferroelectric Random Access Memory，FRAM)、相变存储器(Phase Change Memory，PCM)、石墨烯存储器等。易失性存储器可包括随机存取存储器(Random Access Memory，RAM)或外部高速缓冲存储器等。作为说明而非局限，RAM可以是多种形式，比如静态随机存取存储器(Static Random Access Memory，SRAM)或动态随机存取存储器(Dynamic RandomAccess Memory，DRAM)等。本申请所提供的各实施例中所涉及的数据库可包括关系型数据库和非关系型数据库中至少一种。非关系型数据库可包括基于区块链的分布式数据库等，不限于此。本申请所提供的各实施例中所涉及的处理器可为通用处理器、中央处理器、图形处理器、数字信号处理器、可编程逻辑器、基于量子计算的数据处理逻辑器等，不限于此。Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage In the medium, when the computer program is executed, it may include the processes of the above-mentioned method embodiments. Wherein, any reference to a memory, a database or other media used in the various embodiments provided in this application may include at least one of a non-volatile memory and a volatile memory. Non-volatile memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetic variable memory (Magnetoresistive Random Memory) Access Memory, MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory may include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration and not limitation, the RAM may be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM). The databases involved in the various embodiments provided in this application may include at least one of relational databases and non-relational databases. The non-relational database may include a blockchain-based distributed database, etc., but is not limited thereto. The processors involved in the various embodiments provided in this application may be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, data processing logic devices based on quantum computing, etc., and are not limited to this.

以上实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。The technical features of the above embodiments can be combined arbitrarily. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features It is considered to be the range described in this specification.

以上所述实施例仅表达了本申请的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对本申请专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本申请构思的前提下，还可以做出若干变形和改进，这些都属于本申请的保护范围。因此，本申请的保护范围应以所附权利要求为准。The above-mentioned embodiments only represent several embodiments of the present application, and the descriptions thereof are relatively specific and detailed, but should not be construed as a limitation on the scope of the patent of the present application. It should be pointed out that for those skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the scope of protection of the present application should be determined by the appended claims.

Claims (10)

1. A method of radar calibration, the method comprising:
acquiring first point cloud data received by a reference radar in a moving process according to a preset route and second point cloud data received by a radar to be calibrated in the same scene; at least one position exists in the process that the reference radar moves to the area where the radar to be calibrated is located, so that the visible range of the reference radar comprises the visible range of the radar to be calibrated; reflectors with different shapes are arranged in the visible ranges of different radars to be calibrated; the first point cloud data and the second point cloud data both comprise point cloud data reflected by the reflector;
and matching the first point cloud data and the second point cloud data according to a matching algorithm to obtain an external reference matrix of the radar to be calibrated under a reference coordinate system, wherein the reference coordinate system is a coordinate system established by taking the initial position of the reference radar as an origin.
2. The method according to claim 1, wherein after establishing a reference coordinate system with an initial position of the reference radar as an origin, the method further comprises:
acquiring an initial coordinate of the radar to be calibrated under the reference coordinate system;
taking the initial coordinate of the radar to be calibrated as an initialization matrix parameter of the matching algorithm;
the matching the first point cloud data and the second point cloud data according to a matching algorithm to obtain an external reference matrix of the radar to be calibrated under a reference coordinate system comprises the following steps:
and matching the first point cloud data and the second point cloud data by adopting a matching algorithm with the initialized matrix parameters to obtain an external reference matrix of the radar to be calibrated under a reference coordinate system.
3. The method according to claim 2, wherein the matching the first point cloud data and the second point cloud data by using the matching algorithm with the initialized matrix parameters to obtain an external reference matrix of the radar to be calibrated in a reference coordinate system comprises:
generating map data to be matched according to the first point cloud data;
obtaining a standard normal distribution parameter of the first point cloud data according to the map data to be matched;
obtaining a standard normal distribution parameter of the second point cloud data according to the second point cloud data and the initialization matrix parameter;
and obtaining an external reference matrix of the radar to be calibrated under the reference coordinate system according to the standard normal distribution parameters of the first point cloud data and the standard normal distribution parameters of the second point cloud data.
4. The method according to claim 1, wherein the matching the first point cloud data and the second point cloud data according to a matching algorithm to obtain an external reference matrix of the radar to be calibrated in a reference coordinate system comprises:
acquiring first sub-point cloud data in the first point cloud data, wherein the acquisition time range of the first point cloud data is the same as that of the second point cloud data;
and matching the first sub-point cloud data and the second point cloud data according to a matching algorithm to obtain an external reference matrix of the radar to be calibrated under a reference coordinate system.
5. The method of claim 1, wherein the reflectors comprise circular reflectors, triangular reflectors, and polygonal reflectors.
6. A method of validating radar calibration, the method comprising:
acquiring third point cloud data received by a radar to be verified by scanning a preset reference plane;
converting the third point cloud data received by each radar to be verified into the same coordinate system according to the external parameter matrix of the radar to be verified to obtain fourth point cloud data; the external reference matrix is obtained according to the radar calibration method of any one of claims 1 to 5;
and determining whether the radar calibration result is accurate or not according to the flatness of the fourth point cloud data.
7. A radar calibration apparatus, the apparatus comprising:
the point cloud acquisition module is used for acquiring first point cloud data received by the reference radar in the moving process according to a preset route and second point cloud data received by the radar to be calibrated in the same scene; at least one position exists in the process that the reference radar moves to the area where the radar to be calibrated is located, so that the visible range of the reference radar comprises the visible range of the radar to be calibrated; reflectors with different shapes are arranged in the visible ranges of different radars to be calibrated; the first point cloud data and the second point cloud data both comprise point cloud data reflected by the reflector;
and the point cloud matching module is used for matching the first point cloud data and the second point cloud data according to a matching algorithm to obtain an external reference matrix of the radar to be calibrated under a reference coordinate system, wherein the reference coordinate system is a coordinate system established by taking the initial position of the reference radar as an origin.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 6 when executed by a processor.
CN202210371627.2A 2022-04-11 2022-04-11 Radar calibration and verification method and device, computer equipment and storage medium Pending CN114814750A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210371627.2A CN114814750A (en) 2022-04-11 2022-04-11 Radar calibration and verification method and device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210371627.2A CN114814750A (en) 2022-04-11 2022-04-11 Radar calibration and verification method and device, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114814750A true CN114814750A (en) 2022-07-29

Family

ID=82534091

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210371627.2A Pending CN114814750A (en) 2022-04-11 2022-04-11 Radar calibration and verification method and device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114814750A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024219783A1 (en) * 2023-04-21 2024-10-24 한국전자기술연구원 Device and method for using spatial voxelization to determine location of object sensed by radar

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021031157A1 (en) * 2019-08-21 2021-02-25 深圳市速腾聚创科技有限公司 Extrinsic parameter calibration method and apparatus, computing device and computer storage medium
CN112462350A (en) * 2020-12-10 2021-03-09 苏州一径科技有限公司 Radar calibration method and device, electronic equipment and storage medium
WO2021253193A1 (en) * 2020-06-15 2021-12-23 深圳市大疆创新科技有限公司 Calibration method and calibration apparatus for external parameters of multiple groups of laser radars, and computer storage medium
CN114152935A (en) * 2021-11-19 2022-03-08 苏州一径科技有限公司 Method, device and equipment for evaluating radar external parameter calibration precision
CN114252868A (en) * 2020-09-24 2022-03-29 北京万集科技股份有限公司 Laser radar calibration method and device, computer equipment and storage medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021031157A1 (en) * 2019-08-21 2021-02-25 深圳市速腾聚创科技有限公司 Extrinsic parameter calibration method and apparatus, computing device and computer storage medium
WO2021253193A1 (en) * 2020-06-15 2021-12-23 深圳市大疆创新科技有限公司 Calibration method and calibration apparatus for external parameters of multiple groups of laser radars, and computer storage medium
CN114252868A (en) * 2020-09-24 2022-03-29 北京万集科技股份有限公司 Laser radar calibration method and device, computer equipment and storage medium
CN112462350A (en) * 2020-12-10 2021-03-09 苏州一径科技有限公司 Radar calibration method and device, electronic equipment and storage medium
CN114152935A (en) * 2021-11-19 2022-03-08 苏州一径科技有限公司 Method, device and equipment for evaluating radar external parameter calibration precision

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024219783A1 (en) * 2023-04-21 2024-10-24 한국전자기술연구원 Device and method for using spatial voxelization to determine location of object sensed by radar

Similar Documents

Publication Publication Date Title
CN110031824B (en) Laser radar combined calibration method and device
KR102235827B1 (en) Method and apparatus for generating grid maps
CN111429574B (en) Mobile robot positioning method and system based on three-dimensional point cloud and vision fusion
CN103703490B (en) For generation of the equipment of three-dimensional feature data and the method for generation of three-dimensional feature data
US20150314443A1 (en) Visual-based obstacle detection method and apparatus for mobile robot
CN113111513B (en) Sensor configuration scheme determining method and device, computer equipment and storage medium
CN113031004A (en) Unmanned ship water surface target detection and path planning method based on three-dimensional laser radar
CN116993942A (en) Three-dimensional reconstruction and volume measurement method and system for conical object and unmanned aerial vehicle
CN113192174A (en) Mapping method and device and computer storage medium
Kawashima et al. Finding the next-best scanner position for as-built modeling of piping systems
Schulz et al. Efficient map representations for multi-dimensional normal distributions transforms
KR102450139B1 (en) GLOBAL LOCALIZTION APPARATUS AND METHOD IN DYNAMIC ENVIRONMENTS USING 3D LiDAR SCANNER
Li et al. Registration‐free point cloud generation technique using rotating mirrors
CN111598941A (en) Method, device and equipment for measuring gradient of tower and storage medium
CN114814750A (en) Radar calibration and verification method and device, computer equipment and storage medium
CN115168788B (en) Method, device, equipment and medium for determining satellite remote sensing big data
JP2020135764A (en) Three-dimensional object modeling method, three-dimensional object modeling device, server, three-dimensional model creation system, and program
CN117078870A (en) Road environment three-dimensional reconstruction method integrating high-precision map and laser sparse point cloud
CN113313629B (en) Intersection automatic identification method, system and model preservation method and system
CN117590362B (en) Multi-laser radar external parameter calibration method, device and equipment
CN117075171B (en) Pose information determining method, device and equipment of laser radar and storage medium
CN112084854A (en) Obstacle detection method, obstacle detection device and robot
CN111765883A (en) Monte Carlo positioning method and equipment for robot and storage medium
CN116894870A (en) Image target positioning method, system, electronic equipment and storage medium
CN114419250B (en) Point cloud data vectorization method and device and vector map generation method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination